© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 16217
    Prev
    Next
    INDEX
    Explanations

    numeric values and patterns in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.14
    2:0.08
    3:0.04
    4:0.03
    5:0.01
    6:0.14
    7:0.16
    8:0.02
    9:0.02
    10:0.10
    11:0.03
    Negative Logits
    Charl
    -2.54
     McL
    -2.46
     Mahmoud
    -2.42
     Thom
    -2.40
     Ni
    -2.39
     Tyler
    -2.39
     semin
    -2.38
     taunt
    -2.37
    ouver
    -2.34
     Tav
    -2.33
    POSITIVE LOGITS
    ubis
    2.27
     beetle
    2.26
     wedge
    2.21
     Dove
    2.21
    iamond
    2.17
    ibur
    2.15
     webs
    2.15
     Gears
    2.13
    hedon
    2.11
    244
    2.09
    Activations Density 0.008%

    No Known Activations